论文标题
斯巴达：阿拉伯语的演讲者分析
SPARTA: Speaker Profiling for ARabic TAlk
论文作者
论文摘要
本文提出了一种新颖的方法，可以自动估计来自阿拉伯语的三个说话者特征：性别，情感和方言。在对不同的文本分类任务显示出令人鼓舞的结果后，本文使用多任务学习（MTL）方法用于阿拉伯语语音分类任务。该数据集是从六个公开可用数据集组装的。首先，对数据集进行了编辑，并将其彻底分为火车，开发和测试集（向公众开放），并为整个论文中的每个任务和数据集设置了基准测试。然后，探索了三个不同的网络：长期短期存储器（LSTM），卷积神经网络（CNN）和完全连接的神经网络（FCNN），涉及五种不同类型的特征：两个原始功能（MFCC和MEL）和三个预训练的矢量（I-e-vectors，i-ewectors，d-ewtors和x-vectors）。 LSTM和CNN网络是使用原始功能来实现的：MFCC和MEL，其中FCNN在预先训练的向量上进行了探索，同时改变了这些网络的超参数，以获得每个数据集和任务的最佳结果。针对三个任务和六个数据集的单个任务学习（STL）方法对MTL进行了评估，其中MTL和预训练的向量几乎不断优于STL。本文中使用的所有数据和预培训模型均可被公众获取。
This paper proposes a novel approach to an automatic estimation of three speaker traits from Arabic speech: gender, emotion, and dialect. After showing promising results on different text classification tasks, the multi-task learning (MTL) approach is used in this paper for Arabic speech classification tasks. The dataset was assembled from six publicly available datasets. First, The datasets were edited and thoroughly divided into train, development, and test sets (open to the public), and a benchmark was set for each task and dataset throughout the paper. Then, three different networks were explored: Long Short Term Memory (LSTM), Convolutional Neural Network (CNN), and Fully-Connected Neural Network (FCNN) on five different types of features: two raw features (MFCC and MEL) and three pre-trained vectors (i-vectors, d-vectors, and x-vectors). LSTM and CNN networks were implemented using raw features: MFCC and MEL, where FCNN was explored on the pre-trained vectors while varying the hyper-parameters of these networks to obtain the best results for each dataset and task. MTL was evaluated against the single task learning (STL) approach for the three tasks and six datasets, in which the MTL and pre-trained vectors almost constantly outperformed STL. All the data and pre-trained models used in this paper are available and can be acquired by the public.
